© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53437
    Prev
    Next
    INDEX
    Explanations

    war and conflicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é½
    -0.10
    åħį
    -0.10
    äºĭæķħåıijçĶŁ
    -0.09
    楼主
    -0.09
    åĵģç§į
    -0.09
    èĬ°
    -0.09
    èµ·ãģĵ
    -0.08
    TTY
    -0.08
     Sutton
    -0.08
    ãĥ¥ãĥ¼
    -0.08
    POSITIVE LOGITS
    ç¼
    0.09
    WithMany
    0.08
    Fld
    0.08
     коÑĤоÑĢ
    0.08
    æijĺ
    0.08
    UNET
    0.08
    æĿĪ
    0.08
    loor
    0.08
    zeug
    0.07
    _ent
    0.07
    Activations Density 0.023%

    No Known Activations